Vision and Learning Group

Vision and Learning Group's repositories

DA_Detection

Implementation of "Strong-Weak Distribution Alignment for Adaptive Object Detection"

Language:PythonMIT345 9 46

SSDA_MME

Semi-supervised Domain Adaptation via Minimax Entropy

Language:PythonMIT290 7 8

R-C3D

code for R-C3D

Language:Jupyter NotebookMIT253 21 59

VisionLearningGroup.github.io

Language:CSS182 17 18

taskcv-2017-public

Language:Python169 15 7

DAL

Domain agnostic learning with disentangled representations

Language:Python143 8 6

DANCE

repository for Universal Domain Adaptation through Self-supervision

Language:PythonMIT123 4 10

OVANet

Repository for OVANet

Language:PythonMIT83 3 6

visda-2019-public

Language:Python58 11 8

OP_Match

Language:PythonMIT57 2 10

Text-to-Clip_Retrieval

Implementation for "Multilevel Language and Vision Integration for Text-to-Clip Retrieval"

Language:Jupyter NotebookMIT46 7 7

visda-2018-public

Language:Python45 10 24

visda21-dev

Language:PythonMIT45 11 10

CDS

CDS: Cross-Domain Self-supervised Pre-training

Language:PythonMIT26 2 2

Ask_Attend_and_Answer

Ask, Attend and Answer: Exploring Question-Guided Spatial Attention for Visual Question Answering

Language:C++25 4 7

JEDDi-Net

Implementation for "Joint Event Detection and Description in Continuous Video Streams"

Language:Jupyter NotebookMIT22 7 2

UDA_PoseEstimation

Language:PythonMIT19 2 6

Benchmark_Domain_Transfer

Language:PythonMIT15 2 1

MULE

Implementation of "MULE: Multimodal Universal Language Embedding"

Language:PythonMIT14 5 1

SND

Language:PythonMIT12 20

Domain2Vec

7 10 6

mind_back

repository for a paper, Mind the Backbone: Minimizing Backbone Distortion for Robust Object Detection

Language:PythonMIT400

visda-2018

Language:HTMLMIT3 40

SANE

Pytorch implementation of our ECCV paper

Language:PythonMIT2 30

Learning-Similarity-Conditions

Language:Python1 30

visda-2019

Language:CSSMIT1 30

QSPN

Implementation for "Multilevel Language and Vision Integration for Text-to-Clip Retrieval" coming soon

040

visda-2017

Language:HTMLMIT030

visda-2021

Language:CSSMIT030

visda-2022

Domain adaptation for vision challenge

Language:CSSMIT020